AI Rate CardClaude Haiku 4.5 (latest) vs Claude Sonnet 4.6: API price and specs
Claude Sonnet 4.6 is 70% cheaper than Claude Haiku 4.5 (latest) on input price.
Claude Sonnet 4.6 is 70% cheaper than Claude Haiku 4.5 (latest) on output price.
Claude Sonnet 4.6 is 70% cheaper than Claude Haiku 4.5 (latest) on a 1M-in / 200k-out workload.
Claude Sonnet 4.6 has a 400% larger context than Claude Haiku 4.5 (latest).
| Field | Claude Haiku 4.5 (latest) | Claude Sonnet 4.6 |
|---|---|---|
| Lowest input, per 1M | $0.50 +233.3% | $0.15 |
| Median input, per 1M | $1.00 | $3.00 +200% |
| Lowest output, per 1M | $2.50 +233.3% | $0.75 |
| Median output, per 1M | $5.00 | $15.00 +200% |
| Lowest unit price | $0.001 / request | $0.001 / request |
| Cost of 1M in + 200k out | $1.00 +233.3% | $0.30 |
| Context | 200K +80% | 1M |
| Max output | 64K +50% | 128K |
| Providers | 34 +5.6% | 36 |
| Regions | APAC, AU, EU, GLOBAL, IN, JP, US | APAC, AU, EU, GLOBAL, JP, US |
| Accepts | application/pdf, file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text | application/pdf, file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | openrouter | daoxe |
Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.
Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.
Providers selling both
abacus, aihubmix, aiml, amazon-bedrock, anthropic, azure, azure-cognitive-services, cometapi, cortecs, deepinfra, digitalocean, edenai, fastrouter, freemodel, github-copilot, google-vertex, google-vertex-anthropic, helicone, impossibl, jiekou, kilo, meganova, nearai, ofox, opencode, openrouter, orcarouter, perplexity-agent, poe, requesty, trustedrouter, vercel, xpersona, zenmux
Frequently asked questions
Which is cheaper, Claude Haiku 4.5 (latest) or Claude Sonnet 4.6?
Claude Sonnet 4.6 is 70% cheaper than Claude Haiku 4.5 (latest) on input price. Claude Sonnet 4.6 is 70% cheaper than Claude Haiku 4.5 (latest) on output price. Claude Sonnet 4.6 is 70% cheaper than Claude Haiku 4.5 (latest) on a 1M-in / 200k-out workload.
Which has the larger context, Claude Haiku 4.5 (latest) or Claude Sonnet 4.6?
Claude Haiku 4.5 (latest): 200K tokens; Claude Sonnet 4.6: 1M tokens.
Where can I use both Claude Haiku 4.5 (latest) and Claude Sonnet 4.6?
abacus, aihubmix, aiml, amazon-bedrock, anthropic, azure, azure-cognitive-services, cometapi, cortecs, deepinfra, digitalocean, edenai, fastrouter, freemodel, github-copilot, google-vertex, google-vertex-anthropic, helicone, impossibl, jiekou, kilo, meganova, nearai, ofox, opencode, openrouter, orcarouter, perplexity-agent, poe, requesty, trustedrouter, vercel, xpersona, zenmux