One familiar interface.
Choose a model and send a request through an OpenAI-compatible API.
Still paying full price for Claude, GPT, Gemini?
Text, images, and video.
Make more with the models you love.
88 available models · Pay for usage, no subscription
Claude / GPT / Gemini / Grok · See current groups and billing units below
FIG. 001 / The orbital atelierOriginal concept · ImageGen
A spark becomes a picture. A picture becomes a story. Every kind of expression deserves a stage.
01 / IMAGE
02 / IMAGE + TEXT Artwork: original ImageGen design examples.
02 / THE MODEL COLLECTION
Explore models, compare prices, and plan your usage. All the details are right here.
Find your model. Compare the cost. Start making.
4 available modelsUse-case filters reflect output capabilities. No benchmark scores are claimed.
| MODEL | PRICE · OHGROK | VS OFFICIAL | VS OPENROUTER | CONTEXT | MODALITY | STABILITY | ACTION |
|---|---|---|---|---|---|---|---|
image-2OpenAI Economy · Image · 0.12× · Choose groupRequires this group on your API key. Trial limits may apply. | $0.12 / imagePer generated imageSelected group rate | Image input US$8.00 / 1M tokensCached image input US$2.00 / 1M tokens Image output US$30.00 / 1M tokens Text input US$5.00 / 1M tokens Cached text input US$1.25 / 1M tokens Reference: gpt-image-2. Channel variant or alias; direct equivalence is not verified. Standard token pricing. Cost per image varies with size, quality and input; not a per-request quote.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Image | ConfiguredNot verified | API access Calculate |
gpt-image-2OpenAI HD enhancement · Image2 · 0.90× · Choose groupRequires this group on your API key. Trial limits may apply. | $0.063 / requestPer image requestRequest count, not returned image count | Image input US$8.00 / 1M tokensCached image input US$2.00 / 1M tokens Image output US$30.00 / 1M tokens Text input US$5.00 / 1M tokens Cached text input US$1.25 / 1M tokens Standard token pricing. Cost per image varies with size, quality and input; not a per-request quote.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Image | ConfiguredNot verified | API access Calculate |
gpt-image-2.5-flareOpenAI HD enhancement · Image2 · 0.90× · Choose groupRequires this group on your API key. Trial limits may apply. | $0.063 / requestPer image requestRequest count, not returned image count | Image input US$8.00 / 1M tokensCached image input US$2.00 / 1M tokens Image output US$30.00 / 1M tokens Text input US$5.00 / 1M tokens Cached text input US$1.25 / 1M tokens Standard token pricing. Cost per image varies with size, quality and input; not a per-request quote.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Image | ConfiguredNot verified | API access Calculate |
gpt-image-2.5-sunburstOpenAI HD enhancement · Image2 · 0.90× · Choose groupRequires this group on your API key. Trial limits may apply. | $0.063 / requestPer image requestRequest count, not returned image count | Image input US$8.00 / 1M tokensCached image input US$2.00 / 1M tokens Image output US$30.00 / 1M tokens Text input US$5.00 / 1M tokens Cached text input US$1.25 / 1M tokens Standard token pricing. Cost per image varies with size, quality and input; not a per-request quote.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Image | ConfiguredNot verified | API access Calculate |
grok-imagine-imagexAI Multiple resolutions · Grok Image · 0.20× · Choose groupRequires this group on your API key. Trial limits may apply. | $0.005 / requestPer image requestRequest count, not returned image count | Image output US$0.02 / imagePer generated image; the site charges per request.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Image | ConfiguredNot verified | API access Calculate |
grok-imagine-image-2.0xAI Multiple resolutions · Grok Image · 0.20× · Choose groupRequires this group on your API key. Trial limits may apply. | $0.005 / requestPer image requestRequest count, not returned image count | Image output US$0.04 / imagePer generated image; the site charges per request.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Image | ConfiguredNot verified | API access Calculate |
grok-imagine-image-litexAI Multiple resolutions · Grok Image · 0.20× · Choose groupRequires this group on your API key. Trial limits may apply. | $0.005 / requestPer image requestRequest count, not returned image count | No separate public quoteNo separate Lite quote; the public list names Imagine Image and Image 2.0.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Image | ConfiguredNot verified | API access Calculate |
image-2-proOpenAI Economy · Image · 0.12× · Choose groupRequires this group on your API key. Trial limits may apply. | $0.24 / imagePer generated imageSelected group rate | Image input US$8.00 / 1M tokensCached image input US$2.00 / 1M tokens Image output US$30.00 / 1M tokens Text input US$5.00 / 1M tokens Cached text input US$1.25 / 1M tokens Reference: gpt-image-2. Channel variant or alias; direct equivalence is not verified. Standard token pricing. Cost per image varies with size, quality and input; not a per-request quote.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Image | ConfiguredNot verified | API access Calculate |
image-2.5-sunburstOpenAI Economy · Image · 0.12× · Choose groupRequires this group on your API key. Trial limits may apply. | $0.24 / imagePer generated imageSelected group rate | Image input US$8.00 / 1M tokensCached image input US$2.00 / 1M tokens Image output US$30.00 / 1M tokens Text input US$5.00 / 1M tokens Cached text input US$1.25 / 1M tokens Reference: gpt-image-2.5-sunburst. Channel variant or alias; direct equivalence is not verified. Standard token pricing. Cost per image varies with size, quality and input; not a per-request quote.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Image | ConfiguredNot verified | API access Calculate |
seedream-5.0-liteByteDance Standard · Seedream · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | US$0.07 / imagePer generated imageSelected group rate · US$1 = ¥6.77 · display conversion | Image output US$0.03 / imageStandard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Image | ConfiguredNot verified | API access Calculate |
seedream-5.0-proByteDance Standard · Seedream · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | US$0.15 / imagePer generated imageSelected group rate · US$1 = ¥6.77 · display conversion | Generation ≤1.5K US$0.04 / imageGeneration >1.5K US$0.09 / image Layer extraction ≤1.5K US$0.02 / image Layer extraction >1.5K US$0.04 / image Extra input image <US$0.01 / image First input image is free. Output and layer extraction use separate rates.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Image | ConfiguredNot verified | API access Calculate |
grok-4.6xAI Heavy · Grok · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $1.60 / 1MCache $0.40 Out $4.80Per 1M tokens · standard context · Context tiers apply · see calculator | Input US$2.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$6.00 / 1M tokens Prompt < 200K. At ≥ 200K, all token rates double.Source Checked 2026-10-02 | Input US$2.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$6.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
claude-fable-5Anthropic Enterprise fast · Claude Max · 1.55× · Choose groupRequires this group on your API key. Trial limits may apply. | In $15.50 / 1MCache $1.55 Out $77.50 Write 5m $19.38 · 1h $31.00Per 1M tokens · standard context | Input US$10.00 / 1M tokensCache read US$1.00 / 1M tokens Output US$50.00 / 1M tokens Cache write US$12.50 / 1M tokens Cache write 1h US$20.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$10.00 / 1M tokensCache read US$1.00 / 1M tokens Output US$50.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
claude-fable-5-1Anthropic Enterprise fast · Claude Max · 1.55× · Choose groupRequires this group on your API key. Trial limits may apply. | In $15.50 / 1MCache $0.3875 Out $77.50 Write 5m $19.38 · 1h $31.00Per 1M tokens · standard context | Input US$10.00 / 1M tokensCache read US$0.25 / 1M tokens Output US$50.00 / 1M tokens Cache write US$12.50 / 1M tokens Cache write 1h US$20.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$10.00 / 1M tokensCache read US$0.25 / 1M tokens Output US$50.00 / 1M tokens Reference: anthropic/claude-fable-5.1. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
claude-haiku-4-5-20251001Anthropic Enterprise external · AWS–Claude Kiro · 1.28× · Choose groupRequires this group on your API key. Trial limits may apply. | In $1.28 / 1MCache $0.128 Out $6.40 Write 5m $1.60 · 1h $2.56Per 1M tokens · standard context | Input US$1.00 / 1M tokensCache read US$0.10 / 1M tokens Output US$5.00 / 1M tokens Cache write US$1.25 / 1M tokens Cache write 1h US$2.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$1.00 / 1M tokensCache read US$0.10 / 1M tokens Output US$5.00 / 1M tokens Reference: anthropic/claude-haiku-4.5. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
claude-opus-4-5-20251101Anthropic High cache · Claude Kiro · 0.38× · Choose groupRequires this group on your API key. Trial limits may apply. | In $1.90 / 1MCache $0.19 Out $9.50 Write 5m $2.38 · 1h $3.80Per 1M tokens · standard context | Input US$5.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$25.00 / 1M tokens Cache write US$6.25 / 1M tokens Cache write 1h US$10.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$5.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$25.00 / 1M tokens Reference: anthropic/claude-opus-4.5. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
claude-opus-4-6Anthropic Enterprise fast · Claude Max · 1.55× · Choose groupRequires this group on your API key. Trial limits may apply. | In $7.75 / 1MCache $0.775 Out $38.75 Write 5m $9.69 · 1h $15.50Per 1M tokens · standard context | Input US$5.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$25.00 / 1M tokens Cache write US$6.25 / 1M tokens Cache write 1h US$10.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$5.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$25.00 / 1M tokens Reference: anthropic/claude-opus-4.6. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
claude-opus-4-7Anthropic Enterprise fast · Claude Max · 1.55× · Choose groupRequires this group on your API key. Trial limits may apply. | In $7.75 / 1MCache $0.775 Out $38.75 Write 5m $9.69 · 1h $15.50Per 1M tokens · standard context | Input US$5.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$25.00 / 1M tokens Cache write US$6.25 / 1M tokens Cache write 1h US$10.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$5.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$25.00 / 1M tokens Reference: anthropic/claude-opus-4.7. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
claude-opus-4-8Anthropic Enterprise fast · Claude Max · 1.55× · Choose groupRequires this group on your API key. Trial limits may apply. | In $7.75 / 1MCache $0.775 Out $38.75 Write 5m $9.69 · 1h $15.50Per 1M tokens · standard context | Input US$5.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$25.00 / 1M tokens Cache write US$6.25 / 1M tokens Cache write 1h US$10.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$5.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$25.00 / 1M tokens Reference: anthropic/claude-opus-4.8. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
claude-opus-5Anthropic Enterprise fast · Claude Max · 1.55× · Choose groupRequires this group on your API key. Trial limits may apply. | In $7.75 / 1MCache $0.775 Out $38.75 Write 5m $9.69 · 1h $15.50Per 1M tokens · standard context | Input US$5.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$25.00 / 1M tokens Cache write US$6.25 / 1M tokens Cache write 1h US$10.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$5.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$25.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
claude-opus-5-5Anthropic Enterprise fast · Claude Max · 1.55× · Choose groupRequires this group on your API key. Trial limits may apply. | In $6.20 / 1MCache $0.31 Out $31.00 Write 5m $7.75 · 1h $12.40Per 1M tokens · standard context | Input US$4.00 / 1M tokensCache read US$0.20 / 1M tokens Output US$20.00 / 1M tokens Cache write US$5.00 / 1M tokens Cache write 1h US$8.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$4.00 / 1M tokensCache read US$0.20 / 1M tokens Output US$20.00 / 1M tokens Reference: anthropic/claude-opus-5.5. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
claude-sonnet-4-5-20250929Anthropic High cache · Claude Kiro · 0.38× · Choose groupRequires this group on your API key. Trial limits may apply. | In $1.14 / 1MCache $0.114 Out $5.70 Write 5m $1.43 · 1h $2.28Per 1M tokens · standard context | Input US$3.00 / 1M tokensCache read US$0.30 / 1M tokens Output US$15.00 / 1M tokens Cache write US$3.75 / 1M tokens Cache write 1h US$6.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$3.00 / 1M tokensCache read US$0.30 / 1M tokens Output US$15.00 / 1M tokens Reference: anthropic/claude-sonnet-4.5. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
claude-sonnet-4-6Anthropic Enterprise fast · Claude Max · 1.55× · Choose groupRequires this group on your API key. Trial limits may apply. | In $4.65 / 1MCache $0.465 Out $23.25 Write 5m $5.81 · 1h $9.30Per 1M tokens · standard context | Input US$3.00 / 1M tokensCache read US$0.30 / 1M tokens Output US$15.00 / 1M tokens Cache write US$3.75 / 1M tokens Cache write 1h US$6.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$3.00 / 1M tokensCache read US$0.30 / 1M tokens Output US$15.00 / 1M tokens Reference: anthropic/claude-sonnet-4.6. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
claude-sonnet-5Anthropic Enterprise fast · Claude Max · 1.55× · Choose groupRequires this group on your API key. Trial limits may apply. | In $3.10 / 1MCache $0.31 Out $15.50 Write 5m $3.88 · 1h $6.20Per 1M tokens · standard context | Input US$2.00 / 1M tokensCache read US$0.20 / 1M tokens Output US$10.00 / 1M tokens Cache write US$2.50 / 1M tokens Cache write 1h US$4.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$2.00 / 1M tokensCache read US$0.20 / 1M tokens Output US$10.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
claude-sonnet-5-5Anthropic Enterprise fast · Claude Max · 1.55× · Choose groupRequires this group on your API key. Trial limits may apply. | In $3.10 / 1MCache $0.31 Out $15.50 Write 5m $3.88 · 1h $6.20Per 1M tokens · standard context | Input US$2.00 / 1M tokensCache read US$0.20 / 1M tokens Output US$10.00 / 1M tokens Cache write US$2.50 / 1M tokens Cache write 1h US$4.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$2.00 / 1M tokensCache read US$0.20 / 1M tokens Output US$10.00 / 1M tokens Reference: anthropic/claude-sonnet-5.5. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
codex-auto-reviewOpenAI Official native · Codex API · 2.30× · Choose groupRequires this group on your API key. Trial limits may apply. | In $4.03 / 1MCache $0.4025 Out $32.20Per 1M tokens · standard context | No separate public quoteReview-service identifier; no standalone model API price is published under this name.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
composer-2.5Cursor Heavy · Grok · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.40 / 1MCache $0.16 Out $2.00Per 1M tokens · standard context | Input US$0.50 / 1M tokensCache read US$0.20 / 1M tokens Output US$2.50 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
deepseek-flashDeepSeek Economy · DeepSeek · 0.16× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.0096–$0.0192 / 1MCache $0.000192–$0.000384 Out $0.0384–$0.0768Off-peak–peak · UTC schedule | Input US$0.15–US$0.30 / 1M tokensCache read <US$0.01–<US$0.01 / 1M tokens Output US$0.60–US$1.20 / 1M tokens Off-peak → peak rates. Peak: Mon–Fri 01:00–04:00 and 06:00–10:00 UTC.Source Checked 2026-10-02 | Input US$0.30 / 1M tokensCache read <US$0.01 / 1M tokens Output US$1.20 / 1M tokens Reference: deepseek/deepseek-v4.1-flash. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
deepseek-v4-flashDeepSeek Combined · Chinese models · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.80 / 1MCache $0.016 Out $3.20Per 1M tokens · standard context | Input US$0.15–US$0.30 / 1M tokensCache read <US$0.01–<US$0.01 / 1M tokens Output US$0.60–US$1.20 / 1M tokens Reference: deepseek-flash. Channel variant or alias; direct equivalence is not verified. Off-peak → peak rates. Peak: Mon–Fri 01:00–04:00 and 06:00–10:00 UTC.Source Checked 2026-10-02 | Input US$0.03 / 1M tokensCache read <US$0.01 / 1M tokens Output US$0.06 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
deepseek-v4-flash-0731DeepSeek Combined · Chinese models · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.80 / 1MCache $0.016 Out $3.20Per 1M tokens · standard context | Input US$0.15–US$0.30 / 1M tokensCache read <US$0.01–<US$0.01 / 1M tokens Output US$0.60–US$1.20 / 1M tokens Reference: deepseek-flash. Channel variant or alias; direct equivalence is not verified. Off-peak → peak rates. Peak: Mon–Fri 01:00–04:00 and 06:00–10:00 UTC.Source Checked 2026-10-02 | Input <US$0.01 / 1M tokensCache read <US$0.01 / 1M tokens Output US$1.28 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
deepseek-v4-flash-vision-expDeepSeek Combined · Chinese models · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.80 / 1MCache $0.016 Out $3.20Per 1M tokens · standard context | Input US$0.15–US$0.30 / 1M tokensCache read <US$0.01–<US$0.01 / 1M tokens Output US$0.60–US$1.20 / 1M tokens Reference: deepseek-flash. Channel variant or alias; direct equivalence is not verified. Off-peak → peak rates. Peak: Mon–Fri 01:00–04:00 and 06:00–10:00 UTC.Source Checked 2026-10-02 | Input US$0.22 / 1M tokensCache read <US$0.01 / 1M tokens Output US$0.65 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
deepseek-v4-proDeepSeek Combined · Chinese models · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | In $3.60 / 1MCache $0.12 Out $10.80Per 1M tokens · standard context | Input US$0.66–US$1.32 / 1M tokensCache read US$0.02–US$0.04 / 1M tokens Output US$1.98–US$3.96 / 1M tokens Off-peak → peak rates. Peak: Mon–Fri 01:00–04:00 and 06:00–10:00 UTC.Source Checked 2026-10-02 | Input US$0.21 / 1M tokensCache read US$0.02 / 1M tokens Output US$0.42 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
deepseek-v4-pro-0813DeepSeek Combined · Chinese models · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | In $3.60 / 1MCache $0.12 Out $10.80Per 1M tokens · standard context | Input US$0.66–US$1.32 / 1M tokensCache read US$0.02–US$0.04 / 1M tokens Output US$1.98–US$3.96 / 1M tokens Reference: deepseek-v4-pro. Channel variant or alias; direct equivalence is not verified. Off-peak → peak rates. Peak: Mon–Fri 01:00–04:00 and 06:00–10:00 UTC.Source Checked 2026-10-02 | Input US$0.66 / 1M tokensCache read US$0.02 / 1M tokens Output US$1.98 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
deepseek-v4.1-flashDeepSeek Combined · Chinese models · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.80 / 1MCache $0.016 Out $3.20Per 1M tokens · standard context | Input US$0.15–US$0.30 / 1M tokensCache read <US$0.01–<US$0.01 / 1M tokens Output US$0.60–US$1.20 / 1M tokens Off-peak → peak rates. Peak: Mon–Fri 01:00–04:00 and 06:00–10:00 UTC.Source Checked 2026-10-02 | Input US$0.30 / 1M tokensCache read <US$0.01 / 1M tokens Output US$1.20 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gemini-2.5-flashGoogle CLI · Gemini · 0.50× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.054 / 1MCache $0.0135 Out $0.45Per 1M tokens · standard context | Input US$0.30 / 1M tokensCache read US$0.03 / 1M tokens Output US$2.50 / 1M tokens Standard text-input tier. Audio, storage and tool fees are additional.Source Checked 2026-10-02 | Input US$0.30 / 1M tokensCache read US$0.03 / 1M tokens Output US$2.50 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gemini-2.5-flash-liteGoogle CLI · Gemini · 0.50× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.054 / 1MCache $0.0135 Out $0.45Per 1M tokens · standard context | Input US$0.10 / 1M tokensCache read US$0.01 / 1M tokens Output US$0.40 / 1M tokens Standard text-input tier. Audio, storage and tool fees are additional.Source Checked 2026-10-02 | Input US$0.10 / 1M tokensCache read US$0.01 / 1M tokens Output US$0.40 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gemini-2.5-proGoogle CLI · Gemini · 0.50× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.225 / 1MCache $0.0558 Out $1.80Per 1M tokens · standard context · Context tiers apply · see calculator | Input US$1.25 / 1M tokensCache read US$0.13 / 1M tokens Output US$10.00 / 1M tokens Prompt ≤ 200K. Above 200K: input/cache ×2, output ×1.5. Storage and tools excluded.Source Checked 2026-10-02 | Input US$1.25 / 1M tokensCache read US$0.13 / 1M tokens Output US$10.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gemini-3-flashGoogle Antigravity · Gemini · 0.45× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.0495 / 1MCache $0.00495 Out $0.297Per 1M tokens · standard context | Input US$0.50 / 1M tokensCache read US$0.05 / 1M tokens Output US$3.00 / 1M tokens Reference: gemini-3-flash-preview. Channel variant or alias; direct equivalence is not verified. Standard text-input tier. Audio, storage and tool fees are additional.Source Checked 2026-10-02 | Input US$0.50 / 1M tokensCache read US$0.05 / 1M tokens Output US$3.00 / 1M tokens Reference: google/gemini-3-flash-preview. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gemini-3-flash-previewGoogle CLI · Gemini · 0.50× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.09 / 1MCache $0.009 Out $0.54Per 1M tokens · standard context | Input US$0.50 / 1M tokensCache read US$0.05 / 1M tokens Output US$3.00 / 1M tokens Standard text-input tier. Audio, storage and tool fees are additional.Source Checked 2026-10-02 | Input US$0.50 / 1M tokensCache read US$0.05 / 1M tokens Output US$3.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gemini-3-pro-previewGoogle CLI · Gemini · 0.50× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.36 / 1MCache $0.036 Out $2.16Per 1M tokens · standard context · Context tiers apply · see calculator | No separate public quoteThis retired preview is absent from the current manufacturer rate card. See the OpenRouter quote for the listed version.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gemini-3.1-flash-liteGoogle CLI · Gemini · 0.50× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.09 / 1MCache $0.009 Out $0.54Per 1M tokens · standard context | Input US$0.25 / 1M tokensCache read US$0.03 / 1M tokens Output US$1.50 / 1M tokens Standard text-input tier. Audio, storage and tool fees are additional.Source Checked 2026-10-02 | Input US$0.25 / 1M tokensCache read US$0.02 / 1M tokens Output US$1.50 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gemini-3.1-flash-lite-previewGoogle CLI · Gemini · 0.50× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.09 / 1MCache $0.009 Out $0.54Per 1M tokens · standard context | Input US$0.25 / 1M tokensCache read US$0.03 / 1M tokens Output US$1.50 / 1M tokens Standard text-input tier. Audio, storage and tool fees are additional.Source Checked 2026-10-02 | Input US$0.25 / 1M tokensCache read US$0.02 / 1M tokens Output US$1.50 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gemini-3.1-pro-previewGoogle Build · Gemini · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.768 / 1MCache $0.0768 Out $4.61Per 1M tokens · standard context · Context tiers apply · see calculator | Input US$2.00 / 1M tokensCache read US$0.20 / 1M tokens Output US$12.00 / 1M tokens Prompt ≤ 200K. Above 200K: input/cache ×2, output ×1.5. Storage and tools excluded.Source Checked 2026-10-02 | Input US$2.00 / 1M tokensCache read US$0.20 / 1M tokens Output US$12.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gemini-3.5-flashGoogle CLI · Gemini · 0.50× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.27 / 1MCache $0.027 Out $1.62Per 1M tokens · standard context | Input US$1.50 / 1M tokensCache read US$0.15 / 1M tokens Output US$9.00 / 1M tokens Standard text-input tier. Audio, storage and tool fees are additional.Source Checked 2026-10-02 | Input US$1.50 / 1M tokensCache read US$0.15 / 1M tokens Output US$9.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gemini-3.6-flashGoogle Build · Gemini · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.288 / 1MCache $0.0288 Out $1.44Per 1M tokens · standard context | Input US$0.75 / 1M tokensCache read US$0.08 / 1M tokens Output US$3.75 / 1M tokens Promotional rates through 2026-12-31; prices double on 2027-01-01. Storage and tools excluded.Source Checked 2026-10-02 | Input US$0.75 / 1M tokensCache read US$0.08 / 1M tokens Output US$3.75 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gemini-3.7-flashGoogle Build · Gemini · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.288 / 1MCache $0.0288 Out $1.44Per 1M tokens · standard context | Input US$0.75 / 1M tokensCache read US$0.08 / 1M tokens Output US$3.75 / 1M tokens Promotional rates through 2026-12-31; prices double on 2027-01-01. Storage and tools excluded.Source Checked 2026-10-02 | Input US$0.75 / 1M tokensCache read US$0.08 / 1M tokens Output US$3.75 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gemini-3.7-flash-highGoogle Antigravity · Gemini · 0.45× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.07425 / 1MCache $0.007425 Out $0.37125Per 1M tokens · standard context | Input US$0.75 / 1M tokensCache read US$0.08 / 1M tokens Output US$3.75 / 1M tokens Reference: gemini-3.7-flash. Channel variant or alias; direct equivalence is not verified. Promotional rates through 2026-12-31; prices double on 2027-01-01. Storage and tools excluded.Source Checked 2026-10-02 | Input US$0.75 / 1M tokensCache read US$0.08 / 1M tokens Output US$3.75 / 1M tokens Reference: google/gemini-3.7-flash. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gemini-3.8-flashGoogle Build · Gemini · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.288 / 1MCache $0.0288 Out $1.44Per 1M tokens · standard context | Input US$0.75 / 1M tokensCache read US$0.08 / 1M tokens Output US$3.75 / 1M tokens Promotional rates through 2026-12-31; prices double on 2027-01-01. Storage and tools excluded.Source Checked 2026-10-02 | Input US$0.75 / 1M tokensCache read US$0.08 / 1M tokens Output US$3.75 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gemini-3.8-flash-highGoogle Antigravity · Gemini · 0.45× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.07425 / 1MCache $0.00792 Out $0.37125Per 1M tokens · standard context | Input US$0.75 / 1M tokensCache read US$0.08 / 1M tokens Output US$3.75 / 1M tokens Reference: gemini-3.8-flash. Channel variant or alias; direct equivalence is not verified. Promotional rates through 2026-12-31; prices double on 2027-01-01. Storage and tools excluded.Source Checked 2026-10-02 | Input US$0.75 / 1M tokensCache read US$0.08 / 1M tokens Output US$3.75 / 1M tokens Reference: google/gemini-3.8-flash. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
glm-5.2Z.ai Combined · Chinese models · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | In $3.20 / 1MCache $0.80 Out $11.20Per 1M tokens · standard context | Input US$1.40 / 1M tokensCache read US$0.26 / 1M tokens Output US$4.40 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$0.41 / 1M tokensCache read US$0.26 / 1M tokens Output US$3.99 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
glm-5.3Z.ai Combined · Chinese models · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | In $3.20 / 1MCache $0.80 Out $11.20Per 1M tokens · standard context | Input US$1.40 / 1M tokensCache read US$0.26 / 1M tokens Output US$4.40 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$1.40 / 1M tokensCache read US$0.14 / 1M tokens Output US$4.40 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
glm-5.3-flashZ.ai Combined · Chinese models · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.32 / 1MCache $0.092 Out $1.12Per 1M tokens · standard context | Input US$0.15 / 1M tokensCache read US$0.03 / 1M tokens Output US$0.50 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$0.15 / 1M tokensCache read US$0.03 / 1M tokens Output US$0.50 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gpt-5.4OpenAI Official native · Codex API · 2.30× · Choose groupRequires this group on your API key. Trial limits may apply. | In $5.75 / 1MCache $0.575 Out $34.50Per 1M tokens · standard context · Context tiers apply · see calculator | Input US$2.50 / 1M tokensCache read US$0.25 / 1M tokens Output US$15.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$2.50 / 1M tokensCache read US$0.25 / 1M tokens Output US$15.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gpt-5.4-miniOpenAI Official native · Codex API · 2.30× · Choose groupRequires this group on your API key. Trial limits may apply. | In $1.73 / 1MCache $0.1725 Out $10.35Per 1M tokens · standard context | Input US$0.75 / 1M tokensCache read US$0.08 / 1M tokens Output US$4.50 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$0.75 / 1M tokensCache read US$0.08 / 1M tokens Output US$4.50 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gpt-5.5OpenAI Official native · Codex API · 2.30× · Choose groupRequires this group on your API key. Trial limits may apply. | In $11.50 / 1MCache $1.15 Out $69.00Per 1M tokens · standard context · Context tiers apply · see calculator | Input US$5.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$30.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$5.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$30.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gpt-5.6-lunaOpenAI Official native · Codex API · 2.30× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.46 / 1MCache $0.046 Out $2.76 Write 5m $0.575 · 1h Not separately listedPer 1M tokens · standard context · Context tiers apply · see calculator | Input US$0.20 / 1M tokensCache read US$0.02 / 1M tokens Output US$1.20 / 1M tokens Cache write US$0.25 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$0.20 / 1M tokensCache read US$0.02 / 1M tokens Output US$1.20 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gpt-5.6-solOpenAI Official native · Codex API · 2.30× · Choose groupRequires this group on your API key. Trial limits may apply. | In $11.50 / 1MCache $1.15 Out $69.00 Write 5m $14.38 · 1h Not separately listedPer 1M tokens · standard context · Context tiers apply · see calculator | Input US$4.00 / 1M tokensCache read US$0.40 / 1M tokens Output US$20.00 / 1M tokens Cache write US$5.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$2.00 / 1M tokensCache read US$0.20 / 1M tokens Output US$10.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gpt-5.6-terraOpenAI Official native · Codex API · 2.30× · Choose groupRequires this group on your API key. Trial limits may apply. | In $4.60 / 1MCache $0.46 Out $27.60 Write 5m $5.75 · 1h Not separately listedPer 1M tokens · standard context · Context tiers apply · see calculator | Input US$2.00 / 1M tokensCache read US$0.20 / 1M tokens Output US$12.00 / 1M tokens Cache write US$2.50 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$2.00 / 1M tokensCache read US$0.20 / 1M tokens Output US$12.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gpt-6-astraOpenAI Official native · Codex API · 2.30× · Choose groupRequires this group on your API key. Trial limits may apply. | In $23.00 / 1MCache $2.30 Out $115.00 Write 5m $28.75 · 1h Not separately listedPer 1M tokens · standard context · Context tiers apply · see calculator | Input US$10.00 / 1M tokensCache read US$1.00 / 1M tokens Output US$50.00 / 1M tokens Cache write US$12.50 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$10.00 / 1M tokensCache read US$1.00 / 1M tokens Output US$50.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gpt-6-astra-basispointsOpenAI Pro account pool · Codex Pro · 0.55× · Choose groupRequires this group on your API key. Trial limits may apply. | In $5.50 / 1MCache $0.55 Out $27.50 Write 5m $6.88 · 1h Not separately listedPer 1M tokens · standard context · Context tiers apply · see calculator | Input US$10.00 / 1M tokensCache read US$1.00 / 1M tokens Output US$50.00 / 1M tokens Cache write US$12.50 / 1M tokens Reference: gpt-6-astra. Channel variant or alias; direct equivalence is not verified. Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$10.00 / 1M tokensCache read US$1.00 / 1M tokens Output US$50.00 / 1M tokens Reference: openai/gpt-6-astra. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gpt-6-lunaOpenAI Official native · Codex API · 2.30× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.23 / 1MCache $0.023 Out $1.15 Write 5m $0.2875 · 1h Not separately listedPer 1M tokens · standard context · Context tiers apply · see calculator | Input US$0.10 / 1M tokensCache read US$0.01 / 1M tokens Output US$0.50 / 1M tokens Cache write US$0.13 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$0.10 / 1M tokensCache read US$0.01 / 1M tokens Output US$0.50 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gpt-6-solOpenAI Official native · Codex API · 2.30× · Choose groupRequires this group on your API key. Trial limits may apply. | In $4.60 / 1MCache $0.46 Out $23.00 Write 5m $5.75 · 1h Not separately listedPer 1M tokens · standard context · Context tiers apply · see calculator | Input US$2.00 / 1M tokensCache read US$0.20 / 1M tokens Output US$10.00 / 1M tokens Cache write US$2.50 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$2.00 / 1M tokensCache read US$0.20 / 1M tokens Output US$10.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
gpt-6.1-solOpenAI Official native · Codex API · 2.30× · Choose groupRequires this group on your API key. Trial limits may apply. | In $4.60 / 1MCache $0.23 Out $23.00 Write 5m $5.75 · 1h Not separately listedPer 1M tokens · standard context · Context tiers apply · see calculator | Input US$2.00 / 1M tokensCache read US$0.10 / 1M tokens Output US$10.00 / 1M tokens Cache write US$2.50 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$2.00 / 1M tokensCache read US$0.10 / 1M tokens Output US$10.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
grok-4.20-0309-non-reasoningxAI Heavy · Grok · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $1.00 / 1MCache $0.16 Out $2.00Per 1M tokens · standard context · Context tiers apply · see calculator | Input US$1.25 / 1M tokensCache read US$0.20 / 1M tokens Output US$2.50 / 1M tokens Prompt < 200K. At ≥ 200K, all token rates double.Source Checked 2026-10-02 | Input US$1.25 / 1M tokensCache read US$0.20 / 1M tokens Output US$2.50 / 1M tokens Reference: x-ai/grok-4.20. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
grok-4.20-0309-reasoningxAI Heavy · Grok · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $1.00 / 1MCache $0.16 Out $2.00Per 1M tokens · standard context · Context tiers apply · see calculator | Input US$1.25 / 1M tokensCache read US$0.20 / 1M tokens Output US$2.50 / 1M tokens Prompt < 200K. At ≥ 200K, all token rates double.Source Checked 2026-10-02 | Input US$1.25 / 1M tokensCache read US$0.20 / 1M tokens Output US$2.50 / 1M tokens Reference: x-ai/grok-4.20. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
grok-4.20-non-reasoningxAI Heavy · Grok · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $1.00 / 1MCache $0.16 Out $2.00Per 1M tokens · standard context · Context tiers apply · see calculator | Input US$1.25 / 1M tokensCache read US$0.20 / 1M tokens Output US$2.50 / 1M tokens Prompt < 200K. At ≥ 200K, all token rates double.Source Checked 2026-10-02 | Input US$1.25 / 1M tokensCache read US$0.20 / 1M tokens Output US$2.50 / 1M tokens Reference: x-ai/grok-4.20. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
grok-4.20-reasoningxAI Heavy · Grok · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $1.00 / 1MCache $0.16 Out $2.00Per 1M tokens · standard context · Context tiers apply · see calculator | Input US$1.25 / 1M tokensCache read US$0.20 / 1M tokens Output US$2.50 / 1M tokens Prompt < 200K. At ≥ 200K, all token rates double.Source Checked 2026-10-02 | Input US$1.25 / 1M tokensCache read US$0.20 / 1M tokens Output US$2.50 / 1M tokens Reference: x-ai/grok-4.20. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
grok-4.3xAI Heavy · Grok · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $1.00 / 1MCache $0.16 Out $2.00Per 1M tokens · standard context | Input US$1.25 / 1M tokensCache read US$0.20 / 1M tokens Output US$2.50 / 1M tokens Prompt < 200K. At ≥ 200K, all token rates double.Source Checked 2026-10-02 | Input US$1.25 / 1M tokensCache read US$0.20 / 1M tokens Output US$2.50 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
grok-4.3-latestxAI Heavy · Grok · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $1.00 / 1MCache $0.16 Out $2.00Per 1M tokens · standard context | Input US$1.25 / 1M tokensCache read US$0.20 / 1M tokens Output US$2.50 / 1M tokens Reference: grok-4.3. Channel variant or alias; direct equivalence is not verified. Prompt < 200K. At ≥ 200K, all token rates double.Source Checked 2026-10-02 | Input US$1.25 / 1M tokensCache read US$0.20 / 1M tokens Output US$2.50 / 1M tokens Reference: x-ai/grok-4.3. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
grok-4.5xAI Heavy · Grok · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $1.60 / 1MCache $0.40 Out $4.80Per 1M tokens · standard context · Context tiers apply · see calculator | Input US$2.00 / 1M tokensCache read US$0.30 / 1M tokens Output US$6.00 / 1M tokens Prompt < 200K. At ≥ 200K, all token rates double.Source Checked 2026-10-02 | Input US$2.00 / 1M tokensCache read US$0.30 / 1M tokens Output US$6.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
grok-4.5-latestxAI Heavy · Grok · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $1.60 / 1MCache $0.40 Out $4.80Per 1M tokens · standard context | Input US$2.00 / 1M tokensCache read US$0.30 / 1M tokens Output US$6.00 / 1M tokens Reference: grok-4.5. Channel variant or alias; direct equivalence is not verified. Prompt < 200K. At ≥ 200K, all token rates double.Source Checked 2026-10-02 | Input US$2.00 / 1M tokensCache read US$0.30 / 1M tokens Output US$6.00 / 1M tokens Reference: x-ai/grok-4.5. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
grok-4.6-latestxAI Heavy · Grok · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $1.60 / 1MCache $0.40 Out $4.80Per 1M tokens · standard context · Context tiers apply · see calculator | Input US$2.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$6.00 / 1M tokens Reference: grok-4.6. Channel variant or alias; direct equivalence is not verified. Prompt < 200K. At ≥ 200K, all token rates double.Source Checked 2026-10-02 | Input US$2.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$6.00 / 1M tokens Reference: x-ai/grok-4.6. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
grok-4.7xAI Heavy · Grok · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $1.60 / 1MCache $0.40 Out $4.80Per 1M tokens · standard context · Context tiers apply · see calculator | Input US$2.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$6.00 / 1M tokens Prompt < 200K. At ≥ 200K, all token rates double.Source Checked 2026-10-02 | Input US$2.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$6.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
grok-4.7-latestxAI Heavy · Grok · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $1.60 / 1MCache $0.40 Out $4.80Per 1M tokens · standard context · Context tiers apply · see calculator | Input US$2.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$6.00 / 1M tokens Reference: grok-4.7. Channel variant or alias; direct equivalence is not verified. Prompt < 200K. At ≥ 200K, all token rates double.Source Checked 2026-10-02 | Input US$2.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$6.00 / 1M tokens Reference: x-ai/grok-4.7. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
grok-build-0.1xAI Heavy · Grok · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.80 / 1MCache $0.16 Out $1.60Per 1M tokens · standard context | Input US$1.00 / 1M tokensCache read US$0.20 / 1M tokens Output US$2.00 / 1M tokens Prompt < 200K. At ≥ 200K, all token rates double.Source Checked 2026-10-02 | Input US$1.00 / 1M tokensCache read US$0.20 / 1M tokens Output US$2.00 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
grok-build-latestxAI Heavy · Grok · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.80 / 1MCache $0.16 Out $1.60Per 1M tokens · standard context · Context tiers apply · see calculator | Input US$2.00 / 1M tokensCache read US$0.30 / 1M tokens Output US$6.00 / 1M tokens Reference: grok-4.5. Channel variant or alias; direct equivalence is not verified. Prompt < 200K. At ≥ 200K, all token rates double.Source Checked 2026-10-02 | Input US$2.00 / 1M tokensCache read US$0.30 / 1M tokens Output US$6.00 / 1M tokens Reference: x-ai/grok-4.5. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
grok-composer-2.5-fastxAI Heavy · Grok · 0.80× · Choose groupRequires this group on your API key. Trial limits may apply. | In $2.40 / 1MCache $0.40 Out $12.00Per 1M tokens · standard context | Input US$3.00 / 1M tokensCache read US$0.50 / 1M tokens Output US$15.00 / 1M tokens Reference: Composer 2.5 Fast. Channel variant or alias; direct equivalence is not verified. Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
hy4Tencent Combined · Chinese models · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | In $2.40 / 1MCache $0.12 Out $7.20Per 1M tokens · standard context | Input US$0.83 / 1M tokensCache read US$0.04 / 1M tokens Output US$2.50 / 1M tokens Reference: hy4-preview. Channel variant or alias; direct equivalence is not verified. Tencent Cloud international / Singapore rate card.Source Checked 2026-10-02 | Input US$0.83 / 1M tokensCache read US$0.04 / 1M tokens Output US$2.50 / 1M tokens Reference: tencent/hy4-preview. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
hy4-previewTencent Combined · Chinese models · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | In $2.40 / 1MCache $0.12 Out $7.20Per 1M tokens · standard context | Input US$0.83 / 1M tokensCache read US$0.04 / 1M tokens Output US$2.50 / 1M tokens Tencent Cloud international / Singapore rate card.Source Checked 2026-10-02 | Input US$0.83 / 1M tokensCache read US$0.04 / 1M tokens Output US$2.50 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
kimi-k3Moonshot AI Combined · Chinese models · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | In $8.00 / 1MCache $0.80 Out $40.00Per 1M tokens · standard context | Input US$3.00 / 1M tokensCache read US$0.30 / 1M tokens Output US$15.00 / 1M tokens Standard rates; specification tiers and additional charges are listed at source.Source Checked 2026-10-02 | Input US$2.70 / 1M tokensCache read US$0.27 / 1M tokens Output US$13.50 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
minimax-m3MiniMax Combined · Chinese models · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.84 / 1MCache $0.168 Out $3.36Per 1M tokens · standard context · Context tiers apply · see calculator | Input US$0.30 / 1M tokensCache read US$0.06 / 1M tokens Output US$1.20 / 1M tokens Standard context ≤ 512K; 512K–1M costs double. Includes permanent 50% discount.Source Checked 2026-10-02 | Input US$0.30 / 1M tokensCache read US$0.06 / 1M tokens Output US$1.20 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
muse-spark-1.3-contributor-freeMeta Combined · Chinese models · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.10 / 1MCache $0.002 Out $0.20Per 1M tokens · standard context | No separate public quoteThe channel Free variant has no verified separate manufacturer quote.Source Checked 2026-10-02 | Input US$0.10 / 1M tokensCache read <US$0.01 / 1M tokens Output US$0.20 / 1M tokens Reference: meta/muse-spark-1.3-contributor. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
qwen3.8-flashAlibaba Combined · Chinese models · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | In $0.32 / 1MCache $0.04 Out $1.08Per 1M tokens · standard context | Input US$0.11 / 1M tokensCache read US$0.01 / 1M tokens Output US$0.39 / 1M tokens Cache write US$0.18 / 1M tokens Beijing standard list prices; international regions differ.Source Checked 2026-10-02 | Input US$0.15 / 1M tokensCache read US$0.02 / 1M tokens Output US$0.47 / 1M tokens Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
qwen3.8-maxAlibaba Combined · Chinese models · 1.00× · Choose groupRequires this group on your API key. Trial limits may apply. | In $4.80 / 1MCache $0.60 Out $14.40Per 1M tokens · standard context | Input US$1.71 / 1M tokensCache read US$0.21 / 1M tokens Output US$5.14 / 1M tokens Cache write US$2.14 / 1M tokens Beijing standard list prices; international regions differ.Source Checked 2026-10-02 | Input US$2.00 / 1M tokensCache read US$0.25 / 1M tokens Output US$6.00 / 1M tokens Reference: qwen/qwen3.8-max-0902. Channel variant or alias; direct equivalence is not verified. Published standard token quote. Provider, context and time-based overrides may apply; see source.Source Checked 2026-10-02 | —Not verified | Text | ConfiguredNot verified | Try Calculate |
seedance-2.0-fastByteDance Standard · Seedance · 0.95× · Choose groupRequires this group on your API key. Trial limits may apply. | US$5.19 / 1MVideo billing tokens 720p · no reference videoChange specifications in calculator · US$1 = ¥6.77 · display conversion | 480p / 720p · no reference video US$5.29 / 1M video tokens480p / 720p · with reference video US$3.14 / 1M video tokens List prices shown. Eligible enterprises pay 75% until 2026-10-07 14:00 UTC+8, subject to usage caps.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Video | ConfiguredNot verified | API access Calculate |
seedance-2.0ByteDance Standard · Seedance · 0.95× · Choose groupRequires this group on your API key. Trial limits may apply. | US$6.45 / 1MVideo billing tokens 720p · no reference videoChange specifications in calculator · US$1 = ¥6.77 · display conversion | 480p / 720p · no reference video US$6.57 / 1M video tokens480p / 720p · with reference video US$4.00 / 1M video tokens 1080p · no reference video US$7.29 / 1M video tokens 1080p · with reference video US$4.43 / 1M video tokens 4K · no reference video US$3.71 / 1M video tokens 4K · with reference video US$2.29 / 1M video tokens Online list prices. Reference video minimum usage applies.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Video | ConfiguredNot verified | API access Calculate |
seedance-2.0-miniByteDance Standard · Seedance · 0.95× · Choose groupRequires this group on your API key. Trial limits may apply. | US$3.23 / 1MVideo billing tokens 720p · no reference videoChange specifications in calculator · US$1 = ¥6.77 · display conversion | 480p / 720p · no reference video US$3.29 / 1M video tokens480p / 720p · with reference video US$2.00 / 1M video tokens List prices shown. Eligible enterprises pay 40% until 2026-10-07 14:00 UTC+8, subject to usage caps.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Video | ConfiguredNot verified | API access Calculate |
seedance-2.5ByteDance Standard · Seedance · 0.95× · Choose groupRequires this group on your API key. Trial limits may apply. | US$9.82 / 1MVideo billing tokens 720p · no reference videoChange specifications in calculator · US$1 = ¥6.77 · display conversion | 480p / 720p · no reference video US$10.00 / 1M video tokens480p / 720p · with reference video US$6.00 / 1M video tokens 1080p · no reference video US$11.00 / 1M video tokens 1080p · with reference video US$6.57 / 1M video tokens Online list prices. Reference video minimum usage applies.Source Checked 2026-10-02 | Not listed on OpenRouterNo listing for this model in the checked public catalog.Source Checked 2026-10-02 | —Not verified | Video | ConfiguredNot verified | API access Calculate |
No available models match this search. Try another model name or choose All models.
Choose your workflow and frequency. See what your budget can create.
Your workflow and frequency suggest a starting budget. Output follows the selected model and group.
Your budget stays fixed when you change model, group or specifications.
Video capacity uses a duration estimate. Final charges follow returned billing tokens; model support varies by specification.
Model and billing group determine the estimate. A planning budget is not a payment quote.
Recommended starting budget
$100.00
100 planning credits
OHGROK credits · ¥1 = $1
No bonus included
Compare output with the same budget.
Output for the same budget
Current selection
833 images
image-2 · Economy · Image · 0.12×
1K input + 250 output tokens per request
Other use example
833 images
image-2 · Economy · Image · 0.12×
Other use example
26 estimated 5s clips · 720p
seedance-2.0-fast · Standard · Seedance · 0.95×
Other use example
44,642,500 tokens
grok-4.6 · Heavy · Grok · 0.80×
1K input + 250 output tokens per request
These are separate alternatives, not a combined allowance.
One image per work unit at the selected group rate. Whole work units only. Actual charges follow the returned billing usage.
Current selection · cost per work unit $0.12
Current selection · estimated cost $99.96
Budget left over $0.04
Open your wallet to see currently available payment methods.
Account budgets use $ credits: ¥1 = $1. External comparisons use US$ at a fixed display rate of US$1 = ¥7, not a live exchange rate. Billing is unchanged. Planning budgets include no promotional bonus. Check the wallet for available payment methods.
Built for the workflow
Understand the request, follow the task, and see the usage.
Choose a model and send a request through an OpenAI-compatible API.
Submit a video job, check the same task’s status, and retrieve its result.
Review request records and account balance in your shared console.
Clear mechanisms. No mystery numbers.
US$37.20
88.57% less on model usage
Comparable costs below are in US dollars; site credits remain separate.
| PROVIDER | YEAR | MO | DAY |
|---|---|---|---|
| Official | US$42.00 | US$3.50 | US$0.12 |
| OpenRouter | — | — | — |
| ohgrok | US$4.80 | US$0.40 | US$0.01 |
Credits used / month2.8
Account credit cost / month$2.80
Open your wallet to see currently available payment methods. Planning budgets estimate usage costs and are not payment quotes.
View Official price sourceMake it yours
Bring text, images, and video into the tools you already build.
{
"model": "grok-4.5",
"messages": [
{
"role": "user",
"content": "Make it clearer."
}
]
} Example request Draft copy, explain code, and turn unstructured notes into useful output.
Generate images for campaigns, prototypes, and creative experiments.
Submit a video task, follow its progress, and collect the finished clip.
Images and video are available through the API. Examples illustrate the workflow; media previews are not generation receipts. Sample film credit.
Find your modelBudget planning
One budget. More room to create.
Text, images, and video use each model’s billing unit.
10 planned credits
No bonus included
100 planned credits
No bonus included
1,000 planned credits
No bonus included
Open your wallet to see currently available payment methods.
These are planning budgets, not purchasable packages. No promotional bonus is included.
Account budgets use $ credits: ¥1 = $1. External comparisons use US$ at a fixed display rate of US$1 = ¥7, not a live exchange rate. Billing is unchanged.
Text uses separate input, cache-read, cache-write and output token rates; some groups also use context tiers. Image models charge per image or per request, while video uses billable video tokens. Your key group determines the applicable rates. Prices on this page use dollar-marked site credits, with ¥1 credited as $1. External reference prices and cost comparisons are shown separately in US dollars.
Explore model pricesYes, for the supported API routes. Set the base URL to https://api.ohgrok.com/v1 and supply your ohgrok API key and an enabled model ID. Model capabilities differ; use the specific image or video endpoint for those workflows.
Make your first requestSign in or create an account in the shared console, then open API keys. Select a group that includes your model and check its multiplier; different groups can use different billing rules.
Open API keysSubmit a video request once, save the returned task ID, and check that same task’s status. Download the content after it reports completed. The current video experience is API-only; the console’s task records are not a video-generation studio.
Read the video workflowAccount balance is consumed by model usage rather than a monthly subscription. The amounts on this page are budget-planning scenarios, not purchasable packages. Open your wallet to see currently available payment methods. No recharge bonus is included in the published estimates.
View your walletThe current catalog lists 88 models across text, image, and video. Availability depends on your key group, account access, and upstream capacity. Public catalog availability does not mean every listed model has completed a generation test.
Browse the current catalogModel capabilities and billing units can differ. Current access and pricing take precedence over illustrative examples.
Guides & creations
Practical steps from a first request to a finished result.
01 / API basics
Set your base URL, add an API key, and send a text request.
Read guide02 / Image
Choose an image model, submit a prompt, and save the output.
Read guide03 / Video
Start a job, poll its status, and download the completed clip.
Read guide